Results 1 to 10 of about 173,753 (392)
Nightmare at test time: How punctuation prevents parsers from generalizing [PDF]
arXiv, 2018 Punctuation is a strong indicator of syntactic structure, and parsers trained on text with punctuation often rely heavily on this signal. Punctuation is a diversion, however, since human language processing does not rely on punctuation to the same extent, and in informal texts, we therefore often leave out punctuation.
Anders Søgaard +2 more
arxiv +5 more sources
Punctuation, Prosody, and Discourse: Afterthought Vs. Right Dislocation [PDF]
Frontiers in Psychology, 2015 In a reading production experiment, we investigate the impact of punctuation and discourse structure on the prosodic differentiation of right dislocation and afterthought. Both discourse structure and punctuation are likely to affect the prosodic marking
Beatrice Primus, Petra B Schumacher
exaly +4 more sources
Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition [PDF]
International Journal on Natural Language Computing (IJNLC) 11
(6), 2022, 13, 2023 While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting from irregular pausing patterns or slow speakers.
Piyush Behre +3 more
arxiv +3 more sources
Capitalization and Punctuation Restoration: a Survey [PDF]
P\u{a}i\c{s}, V., Tufi\c{s}, D. Capitalization and punctuation
restoration: a survey. Artif Intell Rev (2021), 2021 Ensuring proper punctuation and letter casing is a key pre-processing step towards applying complex natural language processing algorithms. This is especially significant for textual sources where punctuation and casing are missing, such as the raw output of automatic speech recognition systems.
V. Pais, D. Tufiș
arxiv +3 more sources
LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models [PDF]
arXiv, 2023 Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format. Simultaneously, the development of end-to-end ASR models capable of predicting punctuation and capitalization presents ...
Aleksandr Meister +5 more
arxiv +3 more sources
Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus [PDF]
arXiv, 2022 The punctuation restoration task aims to correctly punctuate the output transcriptions of automatic speech recognition systems. Previous punctuation models, either using text only or demanding the corresponding audio, tend to be constrained by real scenes, where unpunctuated sentences are a mixture of those with and without audio. This paper proposes a
Yaoming Zhu +3 more
arxiv +3 more sources
Streaming Punctuation for Long-form Dictation with Transformers [PDF]
8th International Conference on Signal, Image Processing and
Embedded Systems (SIGEM 2022), Volume 12, Number 20, November 2022, 2022 While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers. Transformer sequence tagging models are effective at capturing long bi-directional context, which is crucial for automatic ...
Piyush Behre +3 more
arxiv +3 more sources
Token-Level Supervised Contrastive Learning for Punctuation Restoration [PDF]
Interspeech, 2021 Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performance of downstream tasks, such as intent detection and slot filling. This gives rise to the need for punctuation restoration.
Qiushi Huang +4 more
arxiv +3 more sources
FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers [PDF]
arXiv, 2023 When applying automated speech recognition (ASR) for Belgian Dutch (Van Dyck et al. 2021), the output consists of an unsegmented stream of words, without any punctuation. A next step is to perform segmentation and insert punctuation, making the ASR output more readable and easy to manually correct.
Vincent Vandeghinste, Oliver Guhr
arxiv +3 more sources
Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios [PDF]
arXiv, 2021 Capitalization and punctuation are important cues for comprehending written texts and conversational transcripts. Yet, many ASR systems do not produce punctuated and case-formatted speech transcripts. We propose to use a multi-task system that can exploit the relations between casing and punctuation to improve their prediction performance. Whereas text
R. Pappagari +4 more
arxiv +3 more sources